‹ BackHN Continuity

Thread

Show HN: Cactus Needle 3: 8-29MB automation models can match DeepSeek V4 Flash

236 points · 93 comments · HenryNdubuaku

  1. hirako2000 · · focus · HN ↗
    My thought, the growing number of dubious claims that a tiny model beats LLMs will make any useful innovation be overlooked.

    What's more important than the resource requirements is to highlight what the model simply cannot even attempt to do that general LLMs do decently well.

    In other words, tell me the anti use case clearly so that I don't have to find out myself.

    1. janalsncm · · focus · HN ↗
      An LLM is a Swiss Army knife. This is a corkscrew.

      All of the other tasks a general-purpose LLM can do (write me a poem about pizza, rewrite this code in rust, tell me about the causes of the war of the roses) are unsupported.

      The only use case this supports is converting unstructured text into structured json calls, and doing that quickly in a low memory environment.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.